© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 89913
    Prev
    Next
    INDEX
    Explanations

    animals and observational studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     animal
    -0.11
     Animals
    -0.10
     animals
    -0.10
     dog
    -0.10
     petition
    -0.10
     Dog
    -0.09
     mamm
    -0.09
    sted
    -0.09
     Animal
    -0.09
     dogs
    -0.09
    POSITIVE LOGITS
     cats
    0.10
     plants
    0.10
    iores
    0.10
    cat
    0.10
     pis
    0.10
     fungi
    0.10
    cats
    0.09
     equ
    0.09
     birds
    0.09
    pac
    0.09
    Activations Density 0.167%

    No Known Activations